• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 추계학술대회
• /
• pp.887-890
• /
• 2012

Image recognition is one of the most important research directions of pattern recognition. Image based road automatic identification technology is widely used in current society, the intelligence has become the trend of the times. This paper studied the image segmentation algorithm theory and its application in road signs recognition system. With the help of image processing technique, respectively, on road signs automatic recognition algorithm of three main parts, namely, image segmentation, character segmentation, image and character recognition, made a systematic study and algorithm. The experimental results show that: the image segmentation algorithm to establish road signs recognition model, can make effective use of smart phone system and application.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.715-719
• /
• 1991

In manufacturing process, usually 2-dimensional part drawing is used as a basic data. If a designer wants to recognize 2-dimensional drawing and formulate 3-dimensional shape, a proper feature recognition rule is required as a prerequisite step. These rules are converted Into knowledge base, should be ed separately in the recognition program and can be referenced In similar way of database application. In this paper, basic feature recognition rules are addressed in structure type knowledge base, and the application system is formulated which can be operated separately with existing data driven program.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권2호
• /
• pp.120-126
• /
• 2020

Studies are being conducted regarding falling recognition using sensors on smartphonesto recognize falling in human daily life. These studies use a number of sensors, mostly acceleration sensors, gyro sensors, motion sensors, etc. Falling recognition system processes the values of sensor data by using a falling recognition algorithm and classifies behavior based on thresholds. If the threshold is ambiguous, the accuracy will be reduced. To solve this problem, Deep learning was introduced in the behavioral recognition system. Deep learning is a kind of machine learning technique that computers process and categorize input data rather than processing it by man-made algorithms. Thus, in this paper, we propose a falling recognition application system using deep learning based on smartphones. The proposed system is powered by apps on smartphones. It also consists of three layers and uses DataBase as a Service (DBaaS) to handle big data and address data heterogeneity. The proposed system uses deep learning to recognize the user's behavior, it can expect higher accuracy compared to the system in the general rule base.

• 한국의류산업학회지
• /
• 제11권6호
• /
• pp.887-895
• /
• 2009

The purposes of this study were to provide informations to apparel companies and to contribute the education of clothing consumers through finding out the present status of clothes purchasing behaviors and the degree of the recognition and the application of care labels of the Chinese students in Daegu area. The data were collected from 166 Chinese students through the questionnaire and analyzed by the frequence, t-test, ANOVA, and Scheffe-test using SPSS 12.0. The results were as follows: 1. The main purchasing place was road shops of well-known brands, and the most decisive factor of purchasing was the display style of goods. They purchased 'any time when necessary' and impulsively. They payed mostly by cash and the most affecting factor of purchasing decision was the degree of fitting. 2. The recognition of the necessity of care label was found in 36.7% of respondent and their most rationale was 'for the management of clothes'. The recognition of care labels showed the highest in reliability and the lowest in application. There were significant differences in satisfaction of care label between male and female and in application according to purchasing places. In conclusion, the recognition of the necessity of care labels showed a little high level but relatively low in the understanding and the application.

• Bulletin of the Korean Chemical Society
• /
• 제32권9호
• /
• pp.3400-3404
• /
• 2011

A new rhodamine B-coumarin conjugate (1) capable of recognizing both $Cu^{2+}$ and $Fe^{3+}$ using two different detection modes have been designed and synthesized. The metal ion induced optical changes of 1 were investigated in $CH_3CN-H_2O$ (1:1, v/v, HEPES 50 mM, pH = 7.0) solution. Sensor 1 exhibits selective colorimetric recognition of $Cu^{2+}$ and fluorescent recognition of $Fe^{3+}$ with UV-vis and fluorescence spectroscopy, respectively. Moreover, both of the $Cu^{2+}$ and $Fe^{3+}$ recognition processes are observed to be barely interfered by other coexisting metal ions.

• Bulletin of the Korean Chemical Society
• /
• 제33권11호
• /
• pp.3696-3700
• /
• 2012

The colorimetric and fluorescent cyanide recognition properties of 2-[(9-ethyl-9H-carbazol-3-yl)methylene]-propanedinitrile (1) in $CH_3CN-H_2O$ (2/1, v/v, HEPES 10 mM, pH = 7.0) solution were evaluated. The optical recognition process of probe 1 exhibited high sensitivity and selectivity to cyanide ion with the detection limit of $2.04{\times}10^{-6}$ M and barely interfered by other coexisting anions. The sensing mechanism of probe 1 is speculated to undergo a nucleophilic addition of cyanide to dicyanovinyl group present in compound 1. The colorimetric and fluorescent dual-modal response to cyanide makes probe 1 has a potential utility in cyanide detection.

• 한국정보통신학회논문지
• /
• 제7권5호
• /
• pp.949-954
• /
• 2003

본 연구에서는 지금까지의 GUI 중심의 웹 어플리케이션을 VUI 중심의 웹 어플리케이션으로 구현하기 위한 음성 인식 항공 정보 시스템을 설계 구현하였다. 이러한 ASP(Active Solver Page)로써 구현한 윈도우 서버 기반에서 운용되는 시스템에 관한 Web 관련 ASR(Automatic Speech Recognition)연구가 최근 상당한 연구가 이루어지고 있지만 ASP의 웹과의 제한성으로 인해 시스템의 속도면, 이식성 등에서 제약을 가져왔다. 이와 같은 제약성을 해결하기 위해 본 연구에서는 음성 정보 및 동적 VoiceXML을 구현하는 자바 빈즈(JAVA Beans) 컴포넌트 구조에 대해서 연구하였다. 또한 본 연구에서는 Remote An(Abstract Windows Toolkit)기술을 이용하여 GUI 및 VUI 에서의 음성 및 그래픽 정보를 동시에 전달 가능하게 하는 Voice 웹 브라우징의 가능성을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제21권1호
• /
• pp.69-76
• /
• 2018

Augmented Reality (AR) technology has rapidly been applied to various application areas including e-learning and e-education. Focusing on the design and development of android tablet application, this study targeted to develop infant music education using AR technology. We used a tablet instead of personal computer because it is more easily accessible and more convenient. Our system allows infant users to play with teaching aids like blocks or puzzles to mimic musical play like game. The user sets the puzzle piece on the playground in front of the tablet and presses the play button. Then, the system extracts a region of interest among the images acquired by internal camera and separates the foreground image from the background image. The block recognition software analyzes, recognizes and shows the result using AR technology. In order to have reasonably working recognition ratio, we did experiments with more than 5,000 frames of actual playing scenarios. We found that the recognition rate can be secured up to 95%, when the threshold values are selected well using various condition parameters.

• 한국정보처리학회논문지
• /
• 제7권3호
• /
• pp.1025-1031
• /
• 2000

Pre-existing pattern recognition techniques, in the case of character recognition, have limited on the application field. But CAI character learning system and writer's recognition system are very important parts. The application field of pre-existing system can be expanded in the content that the learning of characters and the recognition of writers in the proposed paper. In order to achieve these goals, the development contents are the following: Firstly, pre-processing method by understanding the image structure is proposed, secondly, recognition of characters are accomplished b the histogram distribution characteristics. Finally, similarity measure functions are defined from standard character pattern for matching of the input character pattern. Also the effectiveness of this system is demonstrated by experimenting the standard primitive image.

• 한국정보통신학회논문지
• /
• 제21권5호
• /
• pp.951-959
• /
• 2017

본 논문에서는 스마트폰으로 음식 메뉴를 촬영한 영상으로부터 글자를 인식하는 안드로이드 기반의 한글 음식 메뉴 인식 어플리케이션을 설계하고 구현한다. Optical Character Recognition (OCR) 기술은 크게 전처리, 인식 그리고 후처리 과정으로 구분된다. 전처리 과정에서는 Maximally Stable Extremal Regions (MSER) 기법을 이용하여 글자를 추출한다. 인식 과정에서는 무료 OCR 엔진인 Tesseract-OCR을 이용하여 글자를 인식한다. 후처리 과정에서는 음식 메뉴에 대한 사전 DB를 이용하여 잘못된 결과를 수정한다. 제안하는 기법의 성능을 평가하기 위해 실제 메뉴판을 DB로 이용하여 인식 성능을 비교 측정하는 실험을 진행하였다. 구글 플레이스토어에 있는 글자 인식 어플리케이션인 OCR Instantly Free, Text Scanner 그리고 Text Fairy와 인식률 측정 실험을 진행하였으며 실험 결과 제안하는 기법이 다른 기법보다 평균적으로 14.1% 높은 인식률을 보여주는 것을 확인하였다.